Guidance for Pooling Multiple Years of NHIS Data

By Julia A. Rivera Drew


Depending on their research question, analysts will commonly pool multiple years of the National Health Interview Survey (NHIS) data together in order to increase sample sizes of particular subpopulations of interest, such as bisexual adults, immigrants, or pregnant women. The complex design of the NHIS, however, requires analysts to take additional steps to correctly construct and analyze pooled NHIS datasets. Moreover, planned changes to the NHIS design implemented in 2019, as well as changes made in response to the COVID-19 pandemic, require additional special handling to correctly analyze datasets combining multiple years of NHIS data. The objectives of this blog post are to: (1) share tips to correctly construct and analyze pooled NHIS datasets and (2) identify resources for more information.

Tips to Correctly Construct and Analyze Pooled NHIS Datasets

1. Create a pooled sampling weight to use with your pooled dataset.

In general, when pooling multiple years of NHIS data together, you will need to create a new sampling weight to use with the pooled sample. To create this new sampling weight, divide the appropriate sampling weight by the number of years within each distinct sample design period. For example, if one wished to estimate the number of children living in families with low or very low food security (FSSTAT) using pooled 2020-2021 NHIS data (e.g., similar to this report), one would need to create a new sampling weight by dividing the sampling weight identified under the “weights” tab for FSSTAT, SAMPWEIGHT, by the number of years pooled together from the same sampling design period (in this case, two). The sum of the pooled weights would then represent the average annual population size for the pooled time period, rather than the total cumulative population size for the pooled time period. For any given combination of variables, refer to information under the “weights” tab for the variables included in your analysis to help select the appropriate sampling weight. The distinct NHIS sample design periods are 1963-1974, 1975-1984, 1985-1994, 1995-2005, 2006-2015, 2016-2018, and 2019-present.

Continue reading…

IPUMS Founder Steven Ruggles Awarded MacArthur Fellowship

By Stacy Nordstrom

Steven Ruggles standing with arms crossed in front of trees
Steven Ruggles, Historical Demographer, 2022 MacArthur Fellow, Minneapolis, MN

Dr. Steven Ruggles, Regents Professor of History and Population Studies and Director of the Institute for Social Research and Data Innovation at the University of Minnesota, has been honored by the John D. and Catherine T. MacArthur Foundation as one of this year’s MacArthur Fellows. Commonly known as the “genius grant”, the fellowship is regarded as one of the most prestigious awards in the United States for intellectual and artistic achievement.

A historical demographer, Dr. Ruggles is renowned for building IPUMS, the world’s largest publicly available database of population statistics, and an invaluable tool for comparative research across time and space.

“I first met Professor Ruggles when I was working at the National Science Foundation. We have since served on working groups together, and I have been repeatedly impressed by the intellectual rigor and human caring he brings to any problem,” said University of Minnesota Executive Vice President and Provost Rachel T.A. Croson. “His dedicated work on IPUMS has significantly advanced our scientific understanding of the human experience, and has provided data for untold numbers of scholars. This recognition is well-deserved and I am proud that Professor Ruggles is a member of our academic community.”

Continue reading…

New to IPUMS USA: The Adjust Monetary Values Feature

By Danika Brockman and the Adjust Monetary Values Team

Introducing the Adjust Monetary Values feature

The team at IPUMS is excited to introduce a brand-new extract feature, Adjust Monetary Values, which gives you the option to adjust monetary variables to constant units in the IPUMS data extract system. We know firsthand how tedious it can be to compare things like income and rent over time when you have to manually adjust for inflation. This feature allows you to request pre-adjusted monetary variables (e.g., INCWAGE) as part of your extract request! The feature is first being released on IPUMS USA, where you will be able to adjust monetary variables to 2010 dollars.

What does the Adjust Monetary Values feature do?

This feature gives you the option to adjust the monetary variables you have added to your data cart into constant dollars, so that all samples in your data cart are comparable across time for your selected monetary variables. IPUMS USA variables are adjusted to 2010 dollars using the Consumer Price Index for All Urban Consumers (CPI-U). For more information about why the CPI-U was chosen as the pricing index for this feature, see the Monetary Adjustment Feature page.

When you add an inflation-adjusted version of a variable to your data cart, the IPUMS data extract system applies the appropriate CPI-U adjustment factor for each sample year to the variable(s) you’ve selected. Your extract will include both the original monetary variable and the inflation-adjusted monetary variable. Special codes (e.g., NIU, missing) will not be affected by the inflation adjustment. Inflation-adjusted versions of variables will assign all specialty (i.e., non-monetary) codes to a code comprised exclusively of “9’s” with a width two digits greater than the largest value in the original variable (e.g., a variable where the maximum monetary value is “8500,” would assign all specialty codes to “999999” and apply a label of “Non-monetary.”) For details on the original specialty codes and their labels, consult the documentation for the original variable on the IPUMS USA website or cross-tab the adjusted and original variables in your statistical program (note that you may want to include a qualifying if statement so you see only the non-monetary codes).

Continue reading…